andersonbcdefg/PD-3M-Tokenized-Cosmos-Tokenizer-DI8x8 download history

andersonbcdefg/PD-3M-Tokenized-Cosmos-Tokenizer-DI8x8 is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 1,469 times (167 in the last 7 days), and 8,855 times in total. It ranks #14,473 among datasets by monthly downloads.

I can't get the dataset viewer to work, sorry. There's about 3M images and captions from Spawning/PD3M. They are resized and center-cropped to 512x512, and then tokenized into discrete tokens with NVIDIA Cosmos-Tokenizer-DI8x8, which reduces the spatial dimension by a factor of 8, resulting in 64

Open andersonbcdefg/PD-3M-Tokenized-Cosmos-Tokenizer-DI8x8 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.